Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis

Abstract

This paper proposes a hierarchical generative model with a multi-grained latent variable to synthesize expressive speech. In recent years, fine-grained latent variables are introduced into the text-to-speech synthesis that enable the fine control of the prosody and speaking styles of synthesized speech. However, the naturalness of speech degrades when these latent variables are obtained by sampling from the standard Gaussian prior. To solve this problem, we propose a novel framework for modeling the fine-grained latent variables, considering the dependence on an input text, a hierarchical linguistic structure, and a temporal structure of latent variables. This framework consists of a multi-grained variational autoencoder, a conditional prior, and a multi-level auto-regressive latent converter to obtain the different time-resolution latent variables and sample the finer-level latent variables from the coarser-level ones by taking into account the input text. Experimental results indicate an appropriate method of sampling fine-grained latent variables without the reference signal at the synthesis stage. Our proposed framework also provides the controllability of speaking style in an entire utterance.

5 pages, accepted to INTERSPEECH 2020, demo page: https://www.rinna.jp/research/interspeech2020/

References in corpus (5)

• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
• Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
• Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
• Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis